CN103425776A - Multi-user repository cooperation method - Google Patents
Multi-user repository cooperation method Download PDFInfo
- Publication number
- CN103425776A CN103425776A CN2013103555854A CN201310355585A CN103425776A CN 103425776 A CN103425776 A CN 103425776A CN 2013103555854 A CN2013103555854 A CN 2013103555854A CN 201310355585 A CN201310355585 A CN 201310355585A CN 103425776 A CN103425776 A CN 103425776A
- Authority
- CN
- China
- Prior art keywords
- subproblem
- knowledge
- knowledge base
- user
- confidence level
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a multi-user repository cooperation method, which comprises the following steps: firstly, converting a problem into a problem tree; assigning a subproblem into a corresponding repository by a subproblem dispatching rule to solve the subproblem; after the subproblem is solved, carrying out answer integration by a blackboard mechanism; and finally, obtaining a final answer, and submitting the final answer to a user by the cooperation of a coordinating rule repository and a knowledge evaluation system. According to the multi-user repository cooperation method disclosed by the invention, the knowledge updating deficiency is solved by the multi-repository real-time relevance, and a rigorous knowledge evaluation system is established to guarantee the accuracy and the reliability degree of an answer fed back to the user finally. Meanwhile, according to the user feedback, the evaluation score of the knowledge is revised in real time to optimize the knowledge structure and the knowledge depth, multi-repository cooperation parallel processing is utilized to solve the problem, and the problem solving capability and efficiency can be improved.
Description
Technical field
The present invention relates to Internet technical field, a kind of multi-user's knowledge base collaboration method is provided.
Background technology
People are endless for the pursuit of knowledge with thirsting for, and the birth of internet and development make us enter the information age.In the face of immense problem and knowledge, how searching out knowledge and the answer oneself wanted most becomes Times ' Demand.
Traditional one of knowledge mode of obtaining is books, such as famous " Encyclopaedia Britannica ".But modern people are more prone to obtain own needed knowledge in network, more crucial is a bit not enough with expansion such as the renewal of " Encyclopaedia Britannica " this class books knowledge, particularly relates to the field in some forward positions." Encyclopaedia Britannica " these class books belong to enclosed knowledge base system, upgrade slower.
Due to forum, may face knowledge while making the user search required knowledge unprofessional for the knowledge base system of the forms such as forum, not comprehensive, or even wrong answer.The answer of obtaining for search engines such as Google, Baidu needs user oneself to go to screen, choose own needed knowledge.Lack a knowledge evaluation degree.
For the defect of prior art, the present invention proposes a kind of real-time system based on multi-user's knowledge base.Take full advantage of the deficiency that colony's wisdom makes up machine learning, utilize the real time correlation of many knowledge bases to solve the problems such as renewal of knowledge deficiency.Set up rigorous knowledge evaluation system in this simultaneously and ensure accuracy and the fiduciary level that finally feeds back to user's answer, carry out the evaluation score of real time modifying knowledge simultaneously according to user's feedback.Thereby optimize the structure of knowledge and the knowledge degree of depth.
Summary of the invention
The object of the present invention is to provide a kind of high efficiency that has, be applicable to extensive and express network, accuracy rate is high, ensures the high a kind of multi-user's knowledge base collaboration method of accuracy Detection accuracy of knowledge when guaranteeing the real-time of knowledge.
The present invention adopts following skill scheme to achieve these goals:
A kind of multi-user's knowledge base collaboration method is characterized in that comprising the following steps:
The first step: utilize problem that pretreatment module submits the user to carry out pre-service according to problem complexity etc., formation problem tree, and be distributed on the problem communal space.Wherein the problem communal space refers to and can deal with problems for displaying, and the virtual dynamic space of process can adopt blackboard mechanism common in the Coordination Treatment technology to carry out the work of the Completion problem communal space in actual applications; The problem that at first pretreatment module is submitted to according to the user is as trunk, then will be by the problem relevant with this problem and subtask respectively as branch branch and leaf node, the most all subproblem layerings of problem are enumerated, from top beginning, progressively expand formation problem tree downwards.
Second step: the problem of the problem communal space is distributed to corresponding sub-knowledge base by subproblem dispatching rules storehouse in succession by problem, makes the sub-knowledge base can parallel processing.Subproblem dispatching rules storehouse refers to searches for retrieval by the node problems of problem tree in all knowledge bases, finds the knowledge base of corresponding subproblem and is distributed to these knowledge bases.In concrete enforcement, can be assigned according to the attribute of subproblem, feature etc., the attribute of each subproblem has all comprised application domain, the application domain in the attribute of the corresponding knowledge base of application domain wherein, the feature of subproblem is to describe for the feature of this subproblem, comprises issuing time, the weight of subproblem, the pointer of father's problem etc.Just can find according to the attribute of subproblem so corresponding sub-knowledge base territory when assigning, and then select corresponding knowledge base according to some codomain (such as time priority, priority weights etc.) in its feature.
The 3rd step: sub-knowledge base is submitted to the problem communal space by result after retrieving and processing subproblem, if having conflict rule between each knowledge base, utilizes the conflict rule storehouse to coordinate to solve.The conflict rule storehouse is in order to solve subproblem priority and adopt the set series of rules set of different knowledge base knowledge level problems while calling knowledge base knowledge.During concrete enforcement, can give the different subproblem node of weights and call priority and the authority that knowledge base is different, the simple algorithm that priority can be higher by the weights greatest priority is realized; Knowledge is adopted degree and can be meaned by confidence level, and the conclusion that finally preferential selection confidence level is larger is as the conclusion of subproblem;
The 4th step: the result of each subproblem that communal space the inside is obtained is integrated the formation answer, and checks on one's answers and estimated;
The 5th step: if, when the 4th step evaluation answer does not meet standard given in advance, will carry out artificial treatment and knowledge base will be fed back, thus the knowledge in the storehouse of refreshing one's knowledge;
The 6th step: the problem answers obtained is submitted to the user.
In technique scheme, the described problem communal space is mainly used for showing problem, the virtual dynamic space of the process of dealing with problems, and we can adopt blackboard coordination mechanism in force, reach the purposes such as problem is issued, process of problem solving is showed, problem is shared.In brief, blackboard can simply seen the intelligent agent of realizing that Knowledge and information is shared, meets feature and the demand of the problem communal space.
In technique scheme, described subproblem dispatching rules storehouse is mainly used in that subproblem is carried out to knowledge base retrieval assigns, while specifically implementing at first according to the problem attribute of subproblem adopt such as the clustering methods such as K-means by subproblem classified, cluster.In classification, cluster process, will adopt the depth-first algorithm to carry out subproblem node traversal, avoid omitting the subproblem node.Then adopt subproblem weights priority principle to carry out the knowledge base assignment, make like this subproblem to be assigned in order in optimum knowledge base and processed, guaranteed that the subproblem processing is able to parallel processing simultaneously, the raising problem solves efficiency.
In technique scheme, described conflict co-ordination principle storehouse:
Identical conditions may meet a plurality of knowledge bases, infer a plurality of relatively independent conclusions, thereby cause the expansion issues that the knowledge combination causes, in concrete enforcement, we can be in the confidence level of the every rule of knowledge base knowledge acquisition stage definitions, thereby select the reasoning of carrying out that confidence level is higher to obtain knowledge, when if the confidence level that net result still can not meet the demands or appearance are wrong, we will carry out abduction, adopt the depth-first algorithm to carry out again according to confidence level, carrying out reasoning from big to small until meet the confidence level requirement.And different knowledge bases call the stage we adopt the higher knowledge base of carrying out of the larger priority of weights of subproblem to call, while for final different knowledge bases, being met the conclusion that confidence level requires, adopt the conclusion of this subproblem of conduct that confidence level is the highest;
The present invention is because adopt technique scheme, so possess following beneficial effect:
One, high efficiency, be applicable to extensive and express network
One of design object of the present invention is the gateway that can be deployed in catenet and express network, thereby can utilize cluster network to carry out express-analysis and cooperative work, thereby many knowledge bases collaboration method that the present invention proposes is the too greatly too complicated inefficiencies that causes in space of dealing with problems.
Two, timely feedback module of the present invention can effectively solve redundancy and the old of knowledge, further improve the accuracy of knowledge, in addition powerful inference machine engine (machine learning) and to utilize the wisdom of entity individual cluster be all the important evidence of the accuracy of guarantee knowledge base knowledge.
Three, real-time, be applicable to the scene to the effectual requirement of knowledge feedback.
The accompanying drawing explanation
Fig. 1 is many knowledge bases coordination model of the present invention.
Embodiment
The present invention adopts the user knowledge base real time correlation, therefore can ensure the real-time of knowledge base the inside knowledge.
Key of the present invention is machine learning and the intelligent combination of entity personal set gunz, makes up the defect that traditional independent machine learning exists.Accompanying drawing 1 is shown in by whole scheme model, and the foundation of user knowledge base and renewal are bases of the present invention, and the cooperation of multi-user's knowledge base is the key of quick solution challenge.
The present invention relate generally to that problem pretreatment module, conflict co-ordination principle storehouse, subproblem are decomposed storehouse, result is synthetic with the enforcement of evaluation module with cooperate.Key step is as follows:
The first step: utilize problem that pretreatment module submits the user to carry out pre-service according to problem complexity etc., formation problem tree, and be distributed on the problem communal space.
Second step: the problem of the problem communal space is decomposed problem by subproblem decomposition rule storehouse, and in succession is distributed to sub-knowledge base, makes the sub-knowledge base can parallel processing.
The 3rd step: sub-knowledge base is submitted to the problem communal space by result after retrieving and processing subproblem.If have conflict rule between each knowledge base, be beneficial to the conflict rule storehouse and coordinate to solve.
The 4th step: the formation answer is integrated in each subproblem answer that communal space the inside is obtained, and checks on one's answers and estimated.
The 5th step: if, when the 4th step evaluation answer does not meet standard given in advance, will carry out artificial treatment and knowledge base will be fed back, thus the knowledge in the storehouse of refreshing one's knowledge.
The 6th step: the problem answers obtained is submitted to the user.
When problem is fairly simple, can directly utilize outside pointer to carry out calling knowledge base, even do not need the decomposition rule storehouse to carry out PROBLEM DECOMPOSITION, when problem is more complicated, can utilize above-mentioned model mechanism to decompose and solve problem, each knowledge base means a knowledge source, contain the required special knowledge of specific area problem solving, can solve relatively complete a, subproblem independently.
When challenge is carried out to resolution process, usually need according to the complexity of problem itself decomposed, dimensionality reduction operation etc., and that subproblem forms relativity according to the primary and secondary of problem attribute is lower, the problem tree node that independence is higher.Can carry out the traversal of ad hoc rules to the problem tree, thereby guarantee can not leave over subproblem, and carry out the integration of result according to the contrary rule of traversal rule after subproblem is processed fully, can guarantee like this rationality and the correctness of result.
Leaf node in the problem tree is all some relatively independent subproblems, give weights for each leaf node, each leaf node is from a task chain of acquisition in subproblem decomposition rule storehouse, task chain points to corresponding knowledge base, if can utilize outside pointer to be called when knowledge base need to be called other relevant knowledge storehouses, and find that in the process of dealing with problems some knowledge base calls the frequent outside pointer that can its outside pointer is set to fix, facilitate each knowledge base to call.
At this piece of knowledge base, in order to obtain in time newer knowledge, we adopt real-time update mechanism, avoid the hysteresis quality of knowledge base knowledge as far as possible, for those common sense knowledge storehouses, according to evaluation module, feed back to knowledge base, make knowledge base knowledge follow up the epoch in time.Knowledge related question for user knowledge base can adopt cluster association according to actual conditions, Attribute Association etc.
Result is synthetic is mainly the subproblem knowledge base to be solved to the answer of submitting to carry out Knowledge Integration with evaluation module, and is estimated according to evaluation mechanism.The evaluation of knowledge base can adopt the qualitative and quantitative mode to be estimated, and wherein qualitative analysis can be taked as expert survey etc.Quantitative test can be taked the multiattribute assessment method.Wherein evaluation index can be selected such as the knowledge base content quality according to actual conditions, Knowledge Base Techniques performance, the ease for use of knowledge base, knowledge base content quantity, the rate of people logging in of knowledge base and the ratio of error of knowledge base etc.
Below enumerate a simple application scenarios: the user has submitted the computer cisco unity malfunction problem of a complexity to, at first problem is carried out to pre-service and obtain the problem tree, his subproblem is likely that software causes that operating system can not normally move, the computer malfunction problem that hardware causes.But such subproblem is still too complicated, need to further decompose, until can not decompose again.Cause that such as decomposing the computer blue screen computer can not normally move, we decompose computer blue screen code subproblem, then the emphasis retrieval is about the knowledge base of computer blue screen code, and submit a question and obtain relevant information until search the answer of blue screen code knowledge base according to the user, and jointly submit to the answer that other knowledge bases obtain, finally according to the weights of subproblem answer, arrange to integrate and give evaluation module, evaluation module provides best a series of answers according to the evaluation index customized, next be exactly that evaluation system feedback and user obtain the feedback obtained according to actual solution situation after answer, it should be noted that the user feedback rank is higher than the priority of evaluation system, but in order to prevent the feedback of malicious user, we need to arrange certain authority to user feedback, and authority give situation and the contribution degree that can in the past use according to the user, the attributes such as specialty degree carry out giving different authorities after comprehensive evaluation.So both can increase user's enthusiasm, and also can utilize cluster wisdom to make up simple machine learning, the deficiency of reasoning.
Claims (5)
1. multi-user's knowledge base collaboration method is characterized in that comprising the following steps:
The first step: utilize problem that pretreatment module submits the user to carry out pre-service according to problem complexity etc., formation problem tree, and be distributed on the problem communal space.
Second step: the problem in the problem communal space obtains subproblem by subproblem dispatching rules storehouse problem is distributed to corresponding sub-knowledge base in succession;
The 3rd step: sub-knowledge base is submitted to the problem communal space by result after retrieving and processing subproblem, if having conflict rule between each knowledge base, utilizes the conflict rule storehouse to coordinate to solve;
Give the different subproblem node of weights and call priority and the authority that knowledge base is different, the simple algorithm that priority can be higher by the weights greatest priority is realized;
Knowledge is adopted degree and can be meaned by confidence level, and the conclusion that finally preferential selection confidence level is larger is as the conclusion of subproblem;
The 4th step: the result of each subproblem that communal space the inside is obtained is integrated the formation answer, and checks on one's answers and estimated;
The 5th step: if, when the 4th step evaluation answer does not meet standard given in advance, will carry out artificial treatment and knowledge base will be fed back, thus the knowledge in the storehouse of refreshing one's knowledge;
The 6th step: the problem answers obtained is submitted to the user.
2. a kind of multi-user's knowledge base coordination model according to claim 1, it is characterized in that: the problem that at first pretreatment module is submitted to according to the user is as trunk, then will be by the problem relevant with this problem and subtask respectively as branch branch and leaf node, the most all subproblem layerings of problem are enumerated, from top beginning, progressively expand formation problem tree downwards.
3. a kind of multi-user's knowledge base coordination model according to claim 1, it is characterized in that comprising the following steps: the described problem communal space is for the virtual dynamic space of showing problem and the process of dealing with problems, employing blackboard coordination mechanism, problem of implementation issue, process of problem solving are showed, problem is shared.
4. a kind of multi-user's knowledge base coordination model according to claim 1 is characterized in that comprising the following steps: described subproblem dispatching rules storehouse is mainly used in that subproblem is carried out to the knowledge base retrieval assigns,
At first according to the problem attribute of subproblem adopt clustering method by subproblem classified, cluster;
In classification, cluster process, will adopt the depth-first algorithm to carry out subproblem node traversal, avoid omitting the subproblem node;
Adopt subproblem weights priority principle to carry out the knowledge base assignment, subproblem all is assigned in order in optimum knowledge base and is processed.
5 claimed a multi-user knowledge of the requirements of a collaborative model , comprising the following steps: a ,,,, ,,,, ,,,, ,,,, ,,,, ,,, ,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,, ,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,, ,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,, ,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,, ,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,, ,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,, ,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,, ,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,, ,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,, ,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,, ,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,, ,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,, ,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,, ,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,, ,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,, ,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,, ,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,,, ,,, ,,,, ,,,, ,,,, ,,,, sub-problem decomposition rule base conflict coordination rule base as follows :
Give the different subproblem node of weights and call priority and the authority that knowledge base is different, knowledge is adopted degree and can be meaned by confidence level, and the conclusion that finally preferential selection confidence level is larger is as the conclusion of subproblem;
The confidence level of the every rule of knowledge base knowledge acquisition stage definitions, select the reasoning of carrying out that confidence level is higher to obtain knowledge, when if the confidence level that net result still can not meet the demands or appearance are wrong, carry out abduction, adopt the depth-first algorithm to carry out again according to confidence level, carrying out reasoning from big to small until meet the confidence level requirement.
And adopt the higher knowledge base of carrying out of the larger priority of weights of subproblem to call in the different knowledge bases stage of calling, while for final different knowledge bases, being met the conclusion of confidence level requirement, adopt the conclusion of this subproblem of conduct that confidence level is the highest.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310355585.4A CN103425776B (en) | 2013-08-15 | 2013-08-15 | A kind of multi-user repository cooperation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310355585.4A CN103425776B (en) | 2013-08-15 | 2013-08-15 | A kind of multi-user repository cooperation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103425776A true CN103425776A (en) | 2013-12-04 |
| CN103425776B CN103425776B (en) | 2016-11-09 |
Family
ID=49650515
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310355585.4A Active CN103425776B (en) | 2013-08-15 | 2013-08-15 | A kind of multi-user repository cooperation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103425776B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104376365A (en) * | 2014-11-28 | 2015-02-25 | 国家电网公司 | Method for constructing information system running rule libraries on basis of association rule mining |
| CN105072195A (en) * | 2015-08-27 | 2015-11-18 | 阔地教育科技有限公司 | Information interaction server, transmitting terminal, processing terminal and information interaction system |
| CN106155522A (en) * | 2016-06-29 | 2016-11-23 | 上海智臻智能网络科技股份有限公司 | Session data process, knowledge base foundation, optimization, exchange method and device |
| CN107193872A (en) * | 2017-04-14 | 2017-09-22 | 深圳前海微众银行股份有限公司 | Question and answer data processing method and device |
| CN108829682A (en) * | 2016-04-08 | 2018-11-16 | 上海智臻智能网络科技股份有限公司 | Computer readable storage medium, intelligent answer method and intelligent answer device |
| CN109214845A (en) * | 2017-07-03 | 2019-01-15 | 优甸网络科技（上海）有限公司 | The product introduction library of application product guiding |
| CN112818186A (en) * | 2021-01-22 | 2021-05-18 | 平安消费金融有限公司 | Information tracking method and device, electronic equipment and storage medium |
| CN113033157A (en) * | 2021-03-20 | 2021-06-25 | 广州快决测信息科技有限公司 | Questionnaire generating method, device and storage medium |
| CN113033156A (en) * | 2021-03-20 | 2021-06-25 | 广州快决测信息科技有限公司 | Logic tree based questionnaire processing method and device and storage medium |
| CN115277061A (en) * | 2022-06-13 | 2022-11-01 | 盈适慧众(上海)信息咨询合伙企业(有限合伙) | Network security service management system and method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1500258A (en) * | 2000-12-22 | 2004-05-26 | ����̩�ϻ���ҽѧ��˾ | Multi-agent collaborative architecture for problem solving and tutoring |
| CN101661570A (en) * | 2009-09-24 | 2010-03-03 | 河北工业大学 | Expert system for measurement of vacuum degree and life management of vacuum arc extinguish chamber and application method |
| CN101916328A (en) * | 2010-07-23 | 2010-12-15 | 东北电力大学 | Virtual electric power operation evaluating and analyzing method based on knowledge synergism |
| CN102902800A (en) * | 2012-10-12 | 2013-01-30 | 西安电子科技大学 | Agent-based intelligent meta search engine system |
-
2013
- 2013-08-15 CN CN201310355585.4A patent/CN103425776B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1500258A (en) * | 2000-12-22 | 2004-05-26 | ����̩�ϻ���ҽѧ��˾ | Multi-agent collaborative architecture for problem solving and tutoring |
| CN101661570A (en) * | 2009-09-24 | 2010-03-03 | 河北工业大学 | Expert system for measurement of vacuum degree and life management of vacuum arc extinguish chamber and application method |
| CN101916328A (en) * | 2010-07-23 | 2010-12-15 | 东北电力大学 | Virtual electric power operation evaluating and analyzing method based on knowledge synergism |
| CN102902800A (en) * | 2012-10-12 | 2013-01-30 | 西安电子科技大学 | Agent-based intelligent meta search engine system |
Non-Patent Citations (1)
| Title |
|---|
| 李敏 等: "基于多知识库协作的信息导航模型研究", 《中国图书馆学报》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104376365B (en) * | 2014-11-28 | 2018-01-09 | 国家电网公司 | A kind of building method in the information system operation rule storehouse based on association rule mining |
| CN104376365A (en) * | 2014-11-28 | 2015-02-25 | 国家电网公司 | Method for constructing information system running rule libraries on basis of association rule mining |
| CN105072195A (en) * | 2015-08-27 | 2015-11-18 | 阔地教育科技有限公司 | Information interaction server, transmitting terminal, processing terminal and information interaction system |
| CN108829682B (en) * | 2016-04-08 | 2022-10-28 | 上海智臻智能网络科技股份有限公司 | Computer readable storage medium, intelligent question answering method and intelligent question answering device |
| CN108829682A (en) * | 2016-04-08 | 2018-11-16 | 上海智臻智能网络科技股份有限公司 | Computer readable storage medium, intelligent answer method and intelligent answer device |
| CN106155522A (en) * | 2016-06-29 | 2016-11-23 | 上海智臻智能网络科技股份有限公司 | Session data process, knowledge base foundation, optimization, exchange method and device |
| CN106155522B (en) * | 2016-06-29 | 2019-03-29 | 上海智臻智能网络科技股份有限公司 | Session data processing, knowledge base foundation, optimization, exchange method and device |
| CN107193872A (en) * | 2017-04-14 | 2017-09-22 | 深圳前海微众银行股份有限公司 | Question and answer data processing method and device |
| CN109214845A (en) * | 2017-07-03 | 2019-01-15 | 优甸网络科技（上海）有限公司 | The product introduction library of application product guiding |
| CN112818186A (en) * | 2021-01-22 | 2021-05-18 | 平安消费金融有限公司 | Information tracking method and device, electronic equipment and storage medium |
| CN113033157A (en) * | 2021-03-20 | 2021-06-25 | 广州快决测信息科技有限公司 | Questionnaire generating method, device and storage medium |
| CN113033156A (en) * | 2021-03-20 | 2021-06-25 | 广州快决测信息科技有限公司 | Logic tree based questionnaire processing method and device and storage medium |
| CN113033157B (en) * | 2021-03-20 | 2022-03-25 | 广州快决测信息科技有限公司 | Questionnaire generating method, device and storage medium |
| CN115277061A (en) * | 2022-06-13 | 2022-11-01 | 盈适慧众(上海)信息咨询合伙企业(有限合伙) | Network security service management system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103425776B (en) | 2016-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103425776A (en) | Multi-user repository cooperation method | |
| US10540965B2 (en) | Semantic re-ranking of NLU results in conversational dialogue applications | |
| US20210326747A1 (en) | Machine learned model framework for screening question generation | |
| US20160203221A1 (en) | System and apparatus for an application agnostic user search engine | |
| US20160171090A1 (en) | Systems and Methods for Collaborative Project Analysis | |
| US20160203523A1 (en) | Domain generic large scale topic expertise and interest mining across multiple online social networks | |
| WO2017197402A2 (en) | Machine-assisted object matching | |
| US9043248B2 (en) | Learning rewrite rules for search database systems using query logs | |
| CN109657072B (en) | Intelligent search WEB system and method applied to government aid decision | |
| CN105843875A (en) | Smart robot-oriented question and answer data processing method and apparatus | |
| WO2019102411A1 (en) | Structuring incoherent nodes by superimposing on a base knowledge graph | |
| US20120209859A1 (en) | Methods and systems to profile individuals and organizations, and to evaluate culture fit | |
| US20230075655A1 (en) | Systems and methods for context-independent database search paths | |
| Jorgensen | Cross-cultural comparisons | |
| JP2013037498A (en) | Information processing apparatus and information processing method | |
| US20180129754A1 (en) | A method and system for searching within a graph-based architecture | |
| US11609926B1 (en) | Methods and systems for social awareness | |
| CN109947770A (en) | A kind of data base query method, terminal device and storage medium | |
| Karbhari et al. | Recommendation system using content filtering: A case study for college campus placement | |
| Zhang et al. | Identifying network public opinion leaders based on markov logic networks | |
| US20180129739A1 (en) | A method and system for defining information within a graph-based architecture | |
| US20200334314A1 (en) | Emergency disposal support system | |
| CN106844934B (en) | Smart city planning and designing expert system and smart city planning and designing method | |
| US11238102B1 (en) | Providing an object-based response to a natural language query | |
| Bogárdi-Mészöly et al. | Tag and topic recommendation systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information |
Inventor after: Zhang Xiaosong Inventor after: Chen Ruidong Inventor after: Niu Weina Inventor after: Wang Dong Inventor after: Chen Ting Inventor after: Pu Fulian Inventor after: Jiang Wei Inventor after: Liao Jun Inventor before: Chen Ting Inventor before: Zhang Xiaosong Inventor before: Chen Ruidong Inventor before: Niu Weina Inventor before: Wang Dong Inventor before: Pu Fulian Inventor before: Jiang Wei Inventor before: Liao Jun |
|
| CB03 | Change of inventor or designer information | ||
| COR | Change of bibliographic data |
Free format text: CORRECT: INVENTOR; FROM: CHEN TING ZHANG XIAOSONG CHEN RUIDONG NIU WEINA WANG DONG PU FULIAN JIANG WEI LIAO JUN TO: ZHANG XIAOSONG CHEN RUIDONG NIU WEINA WANG DONG CHEN TING PU FULIAN JIANG WEI LIAO JUN |
|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |